INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Elite

-0.78

 Avenger

-0.67

 Feminist

-0.66

 Patriarch

-0.65

 Acting

-0.65

 Sovereign

-0.65

 Unified

-0.64

Neg

-0.64

 Nuclear

-0.64

Div

-0.64

POSITIVE LOGITS

etts

0.75

rentices

0.70

lyn

0.68

rices

0.68

psy

0.68

rants

0.67

cribed

0.67

 winters

0.66

gars

0.66

waters

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.